SOURCE-LINKED INTELLIGENCE

LiAM-SAM: Lifecycle-Aware Memory for Robust SAM2-Based MOT

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Segmentation-based multi-object tracking (MOT) with foundation video models such as SAM2 offers strong localization quality, yet remains fragile in crowded, real-world scenes. In detector-prompted SAM2 pipelines, failures typically arise at three stages of the object lifecycle: (i) erroneous or duplicate track initiation, (ii) memory drift during close interactions, and (iii) unreliable re-identification after long occlusions or re-entry. These errors corrupt object memory and accumulate over time, making long-horizon tracking unstable. In this paper, we reframe MOT as a lifecycle memory integ

Read original source ↗ Open in workspace

recordType

paper

region

Global